💡 (New) Checkout our RExBench paper
Can coding agents autonomously implement AI research extensions? Our RExBench is now available on arXiv !
☕️Yukyung Lee
Postdoctoral Associate
Boston University (tinlab.)
I am postdoctoral associate at Boston University, working with Prof. Najoung Kim and Prof. Sebastian Schuster. I received my Ph.D. from Korea University, advised by Prof. Pilsung Kang. During my Ph.D, I was research intern at NAVER and contributed to CLOVA for Writing. I completed my B.S. at HUFS, advised by Prof. Chungmok Lee
My research centers on Applied NLP, with a long-term vision of ‘Building Goal-Oriented Language Intelligence with Robust Evaluation’. My current interests include Language Model Evaluation, Agent, Writing with AI, Conversational AI, and Anomaly Detection.
Interests
- Language Model Evaluation
- LLM Agent
- Writing with AI
- Conversational AI
- Anomaly Detection
Education
PhD Industrial Management & Engineering
Korea University
BSc Industrial Management & Engineering and BA International Finance
HUFS
Recent News
💡 Checkout our new version of CheckEval paper
Our Extended version of CheckEval is now available on arXiv !
🎉 Paper accepted at NAACL 2025 (Industry Track)
Our WritingPath paper has been accepted to NAACL 2025 (Industry Track)!
🎉 Paper accepted at NeurIPS 2024
Our ContAccum paper has been accepted to NeurIPS 2024!
Recent Publications
For an up-to-date list of publications, check out my Google Scholar.
* denotes equal contribution, † denotes equal contribution as senior role.
(2025).
RExBench: Can coding agents autonomously implement AI research extensions?.
preprint.
(2025).
CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists.
Extended version: Under Review | Workshop version: HEAL@CHI2024.
(2025).
Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models.
NAACL 2025 (Industry Track).
(2024).
A Gradient Accumulation Method for Dense Retriever under Memory Constraint.
NeurIPS 2024.
(2024).
DSTEA: Improving Dialogue State Tracking via Entity Adaptive Pre-training.
In Knowledge-Based System (IF = 8.8) and KnowledgeNLP@KDD 2023.